Hugging Face's logo

Rookied
/
rinko_300_labeling

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
rinko_300_labeling / README.md
ikno
Model save
b7b1651 verified
preview code
|
raw
history blame contribute delete
1.71 kB
metadata
license: other
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model-index:
  - name: rinko_300_labeling
    results: []

rinko_300_labeling

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.0068

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-06
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
2.3912 0.9897 48 2.2464
2.2442 2.0 97 2.1167
2.1047 2.9897 145 2.0317
2.05 4.0 194 2.0067
2.0626 4.9485 240 2.0068

Framework versions

  • PEFT 0.7.1
  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1